Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13511
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific dates or time frames

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.76
    dain
    -0.75
    MSN
    -0.71
     Tradable
    -0.67
    bet
    -0.67
    chens
    -0.66
    ivas
    -0.65
    among
    -0.64
    ictionary
    -0.64
    eva
    -0.64
    POSITIVE LOGITS
     end
    1.63
     beginning
    1.27
     conclusion
    1.18
     next
    1.17
     expiration
    1.16
     outset
    1.14
     deadline
    1.12
     autumn
    1.11
     earliest
    1.08
     onset
    1.08
    Activations Density 0.177%

    No Known Activations